This is the documentation for Recommendations AI, Retail Search, and the new Retail console.

PredictResponse

Stay organized with collections Save and categorize content based on your preferences.

Response message for predict method.

JSON representation 
{
  "results": [
    {
      object (PredictionResult)
    }
  ],
  "attributionToken": string,
  "missingIds": [
    string
  ],
  "validateOnly": boolean
}
Fields
results[]

object (PredictionResult)

A list of recommended products. The order represents the ranking (from the most relevant product to the least).
attributionToken

string

A unique attribution token. This should be included in the UserEvent logs resulting from this recommendation, which enables accurate attribution of recommendation model performance.
missingIds[]

string

IDs of products in the request that were missing from the inventory.
validateOnly

boolean

True if the validateOnly property was set in the request.

PredictionResult

PredictionResult represents the recommendation prediction results.

JSON representation 
{
  "id": string,
  "metadata": {
    string: value,
    ...
  }
}
Fields
id

string

ID of the recommended product
metadata

map (key: string, value: value (Value format))

Additional product metadata / annotations.

Possible values:

  • product: JSON representation of the product. Is set if returnProduct is set to true in PredictRequest.params.
  • score: Prediction score in double value. Is set if returnScore is set to true in PredictRequest.params.